Disaster situation marking method, device and equipment for disaster-affected area, medium and program product

Abstract

The embodiment of the invention discloses a disaster situation labeling method for a disaster-affected area, and the method comprises the steps: obtaining the historical disaster situation data of a target area, inputting the historical disaster situation data and a plurality of disaster situation influence factors into a plurality of pre-trained weight detection models, respectively obtaining an initial weight value which is output by each weight detection model and corresponds to each disaster situation influence factor; for each disaster situation influence factor, according to a preset operation mode, processing the initial weight values corresponding to the disaster situation influence factors output by the plurality of weight detection models into target weight values corresponding to the disaster situation influence factors; obtaining a region identification graph corresponding to the target region and disaster situation data of the target region, dividing the region identification graph into a plurality of sub-regions, and obtaining disaster situation influence factor data corresponding to disaster situation influence factors of each sub-region, and according to the disaster situation data of the target area, the plurality of disaster situation influence factor data and the corresponding target weight values, performing disaster situation labeling on the area identification graph. The disaster assessment efficiency and assessment precision of the affected area can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of information processing technology, and in particular to a method, apparatus, equipment, medium and program product for marking disaster conditions in disaster-stricken areas. Background Technology

[0002] Every year, natural disasters cause difficulties in the basic living conditions of people in some affected areas. Therefore, analyzing the severity of disasters in different affected areas and implementing targeted rescue and relief efforts are urgent problems that need to be addressed.

[0003] In existing technologies, different influencing factors are typically assigned weights using expert scoring or entropy weighting methods. The severity of the disaster in different districts and counties is then determined based on the weighted influencing factors, and targeted rescue and relief efforts are then carried out for each district and county.

[0004] However, the expert scoring method is a subjective scoring method, which is highly subjective. Therefore, it has the problem of low accuracy in assessing the severity of disasters. Moreover, when determining the severity of disasters in different regions, it can only be determined down to the district and county level, which makes it impossible to implement precise policies and the degree of precision in disaster relief is poor. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, storage medium, and program product for marking disaster situations in disaster-stricken areas. It can mark disaster situations on regional identification maps based on disaster data of the target area, data of multiple disaster influencing factors, and their corresponding target weight values, thereby improving the efficiency and accuracy of disaster assessment in disaster-stricken areas.

[0006] According to one aspect of the present invention, a method for marking disaster conditions in a disaster-stricken area is provided, characterized in that it includes:

[0007] Historical disaster data for the target area is acquired, and the historical disaster data and multiple disaster influencing factors are input into multiple pre-trained weight detection models to obtain the initial weight value output by each weight detection model corresponding to each disaster influencing factor; wherein, the disaster influencing factors are associated with the disaster type; the weight detection models are trained based on machine learning models;

[0008] For each of the disaster-affecting factors, the initial weight values ​​corresponding to the disaster-affecting factors output by multiple weight detection models are processed into target weight values ​​corresponding to the disaster-affecting factors according to a preset calculation method; wherein, the preset calculation method includes averaging or weighted summation.

[0009] Obtain the regional identification map and disaster data of the target area, divide the regional identification map into multiple sub-regions, obtain the disaster influencing factor data corresponding to the disaster influencing factors of each sub-region, and annotate the regional identification map with disaster data based on the disaster data of the target area, the multiple disaster influencing factor data and their corresponding target weight values.

[0010] According to another aspect of the present invention, a disaster situation marking device for a disaster-stricken area is provided, comprising:

[0011] The initial weight value determination module is used to acquire historical disaster data of the target area, input the historical disaster data and multiple disaster influencing factors into multiple pre-trained weight detection models, and obtain the initial weight value output by each weight detection model corresponding to each disaster influencing factor; wherein, the disaster influencing factors are associated with the disaster type; the weight detection model is trained based on a machine learning model;

[0012] The target weight value determination module is used to process the initial weight values ​​corresponding to the disaster impact factors output by multiple weight detection models into target weight values ​​corresponding to the disaster impact factors for each of the disaster impact factors according to a preset calculation method; wherein, the preset calculation method includes averaging calculation or weighted summation calculation;

[0013] The disaster labeling module is used to obtain the regional identification map and disaster data of the target area, divide the regional identification map into multiple sub-regions, obtain the disaster influencing factor data corresponding to the disaster influencing factors of each sub-region, and label the regional identification map with disaster data based on the disaster data of the target area, the multiple disaster influencing factor data and their corresponding target weight values.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the disaster labeling method for disaster-stricken areas as described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the disaster situation labeling method for disaster-stricken areas as described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the disaster situation labeling method for disaster-stricken areas as described in any embodiment of the present invention.

[0020] This invention, through obtaining historical disaster data of a target area, inputs this historical disaster data and multiple disaster-related influencing factors into multiple pre-trained weight detection models trained based on machine learning models. Each weight detection model outputs an initial weight value corresponding to each disaster-related influencing factor. For each disaster-related influencing factor, the initial weight values ​​output by the multiple weight detection models are processed into target weight values ​​according to a preset calculation method of averaging or weighted summation. This allows for more accurate determination of the weight value corresponding to each disaster-related influencing factor included in each type of disaster. Furthermore, the invention acquires a regional identification map and disaster data for the target area, divides the regional identification map into multiple sub-regions, and obtains disaster-related influencing factor data for each sub-region. Based on the disaster data of the target area, the multiple disaster-related influencing factor data, and their corresponding target weight values, the regional identification map is labeled with disaster information, improving the efficiency and accuracy of disaster assessment in affected areas.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a disaster situation labeling method for disaster-stricken areas provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of another disaster situation labeling method for disaster-stricken areas provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of a disaster situation marking device for a disaster-stricken area provided in Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a disaster labeling method for disaster-stricken areas provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where regional disaster data for each sub-region is determined based on historical disaster data of the target area, and disaster labeling is performed on the regional identification map based on the disaster data of the target area, multiple disaster influencing factors, and their corresponding target weight values. This method can be executed by a disaster labeling device for the disaster-stricken area. This device can be implemented by software and / or hardware and can be integrated into an electronic device, which can be a terminal device or a server device. Figure 1 As shown, the method includes:

[0031] S110. Obtain historical disaster data for the target area, input the historical disaster data and multiple disaster influencing factors into multiple pre-trained weight detection models, and obtain the initial weight value corresponding to each disaster influencing factor output by each weight detection model.

[0032] Among them, the factors affecting the disaster are related to the type of disaster; the weight detection model is trained based on a machine learning model.

[0033] The target area can be a disaster-stricken area affected by different types of disasters and requiring disaster labeling. Multiple different target areas may be generated during a disaster, each corresponding to a different geographical location. This embodiment of the invention does not specifically limit the method of dividing the target areas; those skilled in the art can independently set the method and criteria for dividing the target areas according to labeling requirements. By labeling the disaster information of the target areas, the disaster distribution of each target area can be understood more intuitively and accurately, providing a foundation for disaster relief and assistance in the target areas, and providing reference and basis for refined disaster management. Disaster types can include at least one of flood disasters, typhoon disasters, low-temperature freezing disasters, snow disasters, and drought disasters. Historical disaster data can be obtained after the target area is affected by a disaster, through statistical analysis or disaster data reported by multiple sub-regions within the target area, corresponding to the disaster data of the target area. This embodiment of the invention does not specifically limit the method of obtaining historical disaster data; those skilled in the art can obtain it through different methods according to needs.

[0034] The disaster-influencing factors can be pre-constructed and represent factors that affect the severity or level of disaster in a disaster-stricken area when it is affected by different types of disasters. The data corresponding to these disaster-influencing factors can be generated based on monitoring information or obtained through statistical analysis. This embodiment of the invention does not specifically limit the method of obtaining the data corresponding to these disaster-influencing factors; those skilled in the art can obtain it in different ways as needed. Different disaster types correspond to multiple disaster-influencing factors, and different disaster types may contain different or the same disaster-influencing factors.

[0035] Historical disaster data corresponding to floods may include at least one of the following elements: regional identification information of the affected area, start time of the disaster process, end time of the disaster process, affected population, number of people urgently relocated, affected area of ​​crops, area of ​​crops with no harvest, number of damaged houses, number of collapsed houses, and direct economic losses. Disaster influencing factors corresponding to floods may include at least one of the following factors during the flood disaster period: average rainfall in the affected area, maximum single-day rainfall, cumulative rainfall, flooded area, maximum flood depth, total flood duration, river network density, distance from the regional center to the river channel, topographic index, topographic slope, soil type, vegetation index, total resident population, population density, cultivated land area, number of houses, house structure, GDP, GDP per capita, and flood prevention and mitigation capacity index.

[0036] The regional identification information can be a unique identifier representing the geographical location of the target area, such as the administrative division code or other identifiers corresponding to the target area. The flood disaster time period can be the period from the start time to the end time of the flood disaster process, such as the period from the issuance of a flood disaster warning to its end. The disaster process start time can be the time node when the disaster warning is issued, and the disaster process end time can be the time node when the disaster ends. The flood disaster prevention and mitigation capability index can be a disaster prevention and mitigation capability index determined based on the target area's disaster prevention capability, mitigation capability, and relief capability when encountering a flood disaster. This embodiment of the invention does not specifically limit the method for determining the flood disaster prevention and mitigation capability index.

[0037] Historical disaster data corresponding to typhoon disasters may include at least one of the following elements: regional identification information of the affected area, start time of the disaster process, end time of the disaster process, affected population, number of people urgently relocated, affected area of ​​crops, area of ​​crops with no harvest, number of damaged houses, number of collapsed houses, and direct economic losses. Disaster impact factors corresponding to typhoon disasters include at least one of the following factors during the typhoon disaster period: average rainfall, maximum single-day rainfall, cumulative rainfall, flooded area, maximum flood depth, total flood duration, maximum wind speed, average wind speed, river network density, distance from the regional center to the river channel, topographic index, topographic slope, soil type, vegetation index, total resident population, population density, cultivated land area, number of houses, house structure, GDP, GDP per capita, and typhoon disaster prevention and mitigation capacity index.

[0038] The typhoon disaster time period can be the period from the start time to the end time of the typhoon disaster process, such as the period from the issuance of a typhoon disaster warning to its end. The typhoon disaster prevention and mitigation capability index can be determined based on the disaster prevention capability, mitigation capability, and relief capability of a target area when encountering a typhoon disaster. This embodiment of the invention does not specifically limit the method for determining the typhoon disaster prevention and mitigation capability index.

[0039] Historical disaster data corresponding to low-temperature freezing disasters may include at least one of the following elements: regional identification information of the affected area, start time of the disaster, end time of the disaster, affected population, population requiring emergency living assistance, affected crop area, crop failure area, length of damaged roads, length of damaged power lines, and direct economic losses. Disaster influencing factors corresponding to low-temperature freezing disasters include at least one of the following factors: average daily rainfall, duration of precipitation, average daily temperature, duration of freezing, total resident population, road length, cultivated land area, total length of power lines, GDP, GDP per capita, and low-temperature freezing disaster prevention and mitigation capacity index.

[0040] The low-temperature freezing disaster time period can be the period from the start time to the end time of the disaster process, such as the period from the issuance of a disaster warning to its end. The low-temperature freezing disaster prevention and mitigation capability index can be determined based on the disaster prevention capability, mitigation capability, and relief capability of the target area when encountering a low-temperature freezing disaster. This embodiment of the invention does not specifically limit the method for determining the low-temperature freezing disaster prevention and mitigation capability index.

[0041] Historical disaster data corresponding to snow and ice disasters may include at least one of the following elements: regional identification information of the affected area, start time of the disaster process, end time of the disaster process, affected population, affected crop area, livestock deaths due to the disaster, and direct economic losses. Disaster influencing factors corresponding to snow and ice disasters include at least one of the following factors during the snow and ice disaster period: cumulative snowfall, snow depth, duration of snow cover, total resident population, cultivated land area, number of livestock farmers, livestock numbers, GDP, GDP per capita, and snow and ice disaster prevention and mitigation capacity index.

[0042] The snow and ice disaster time period can be the period from the start time to the end time of the snow and ice disaster process, such as the period from the issuance of a snow and ice disaster warning to its end. The snow and ice disaster prevention and mitigation capability index can be determined based on the disaster prevention capability, mitigation capability, and relief capability of the target area when encountering a snow and ice disaster. This embodiment of the invention does not specifically limit the method for determining the snow and ice disaster prevention and mitigation capability index.

[0043] Historical disaster data corresponding to drought disasters may include at least one of the following: regional identification information of the affected area, start time of the disaster process, end time of the disaster process, affected population, cumulative number of people requiring assistance due to drought, affected area of ​​crops, affected area of ​​grain crops, area of ​​crops with no harvest, area of ​​grain crops with no harvest, livestock facing drinking water difficulties due to drought, and direct economic losses. Disaster influencing factors corresponding to drought disasters include at least one of the following: meteorological drought comprehensive monitoring index of the affected area during the drought disaster period, percentage of rainfall anomaly, percentage of hydrological runoff anomaly, total resident population, agricultural population, cultivated land area, grain crop planting area, livestock numbers, GDP, per capita GDP, and drought prevention and mitigation capacity index.

[0044] The drought disaster time period can be the period from the start time to the end time of the drought disaster process, such as the period from the issuance of a drought disaster warning to its end. The drought prevention and mitigation capacity index can be determined based on the disaster prevention capacity, mitigation capacity, and relief capacity of the target area when encountering a drought disaster. This embodiment of the invention does not specifically limit the method for determining the drought prevention and mitigation capacity index.

[0045] The weight detection model can be a model trained based on a machine learning model, used to determine the initial weight values ​​of disaster-affecting factors. For example, the machine learning model can be a model built using algorithms such as decision trees, random forests, and neural networks. This embodiment of the invention does not specifically limit the specific algorithm of the machine learning model, and those skilled in the art can choose according to their needs.

[0046] The initial weight values ​​can be preliminary, unprocessed weight values ​​output by each weight detection model for each disaster-influencing factor. These initial weight values ​​characterize the relative importance of the disaster-influencing factors to the degree of disaster impact for each target area when encountering different disaster types. It should be noted that the initial weight values ​​output by different weight detection models can be the same or different.

[0047] Specifically, historical disaster data and multiple disaster-influencing factors are input into multiple pre-trained weight detection models. This can be achieved by aligning the historical disaster data and multiple disaster-influencing factors in time and space, based on the geographical and temporal information corresponding to each set of disaster data and the geographical and temporal information corresponding to each of the multiple disaster-influencing factors. Further, the time- and spatially aligned historical disaster data and multiple disaster-influencing factors are input into the multiple pre-trained weight detection models to obtain the initial weight value output by each weight detection model corresponding to each disaster-influencing factor.

[0048] Optionally, the weight detection model can be trained as follows: obtain sample disaster data, multiple sample disaster influencing factor data, and weight labeling information corresponding to each sample disaster influencing factor data; construct a sample set based on the sample disaster data, multiple sample disaster influencing factor data, and weight labeling information corresponding to each sample disaster influencing factor data; input the sample set into multiple pre-built machine learning models to train each machine learning model; and determine the machine learning model as the weight detection model when the machine learning model meets the preset end-of-training conditions.

[0049] The sample region can be a pre-selected disaster-affected area with different disaster types and characteristics used for model training. Sample disaster data can be disaster sample data related to the occurrence and extent of the disaster within the sample region. Sample disaster influencing factor data can be sample data of disaster influencing factors related to the occurrence and extent of the disaster within the sample region. Sample disaster influencing factor data can be obtained by analyzing sample disaster data or directly acquired; this embodiment of the invention does not specifically limit the method of acquiring sample disaster influencing factor data. Weight labeling information can be the weight values ​​labeled for each sample disaster influencing factor data during the training of the weight detection model, used to characterize the relative importance of each sample disaster influencing factor in disaster assessment. The sample set can be a collection of multiple sample regions and their corresponding sample disaster data, sample disaster influencing factor data, and weight labeling information. By continuously learning from the sample set, the model can optimize its parameters, thereby improving its accuracy in disaster assessment. The end-of-training condition can be a standard or condition used during the training of the machine learning model to determine whether the model has reached the expected performance or meets specific requirements. The conditions for ending training can be that the model's accuracy and recall reach a certain threshold, or that the model's training time or number of iterations reaches a preset limit.

[0050] For example, multiple disaster-affected areas with different disaster types and characteristics can be selected as sample areas. Sample disaster data, multiple sample disaster influencing factor data, and corresponding weight annotation information can be collected to construct a sample set. The sample set is then input into multiple pre-built machine learning models for training, and the machine learning model that meets the preset end-of-training conditions is determined as the weight detection model. This improves the accuracy of the model's weight evaluation.

[0051] Specifically, when a target area suffers from different types of disasters and it is necessary to label the disaster situation, the disaster category corresponding to the target area and the historical disaster data corresponding to the disaster category can be obtained. The historical disaster data and multiple disaster influencing factors corresponding to the disaster category of the target area are then input into multiple pre-trained weight detection models. This yields initial weight values ​​for each disaster influencing factor output by each weight detection model, resulting in multiple initial weight values ​​for each disaster influencing factor output by multiple weight detection models. Determining multiple initial weight values ​​for each disaster influencing factor through multiple different weight detection models can improve the accuracy of weight detection, thereby improving the accuracy of disaster assessment of the affected area.

[0052] S120. For each disaster-affecting factor, the initial weight values ​​output by multiple weight detection models corresponding to the disaster-affecting factor are processed into target weight values ​​corresponding to the disaster-affecting factor according to the preset calculation method.

[0053] The preset calculation method can be the calculation method used when processing the initial weight values ​​corresponding to disaster impact factors output by multiple weight detection models into target weight values ​​corresponding to disaster impact factors. The preset calculation method can include averaging or weighted summation, etc., and the calculation method can be selected according to specific needs or scenarios. This invention does not specifically limit the determination method of the preset calculation method. For example, averaging can be performed by summing the initial weight values ​​corresponding to each disaster impact factor output by multiple weight detection models, and then dividing the sum by the number of initial weight values ​​to obtain the target weight value corresponding to each disaster impact factor. Weighted summation can be performed by multiplying the initial weight values ​​corresponding to each disaster impact factor by the preset weight values ​​corresponding to the weight detection models, and then adding all the products to obtain the target weight value corresponding to each disaster impact factor.

[0054] The target weight value can be the final weight value corresponding to each disaster-affecting factor, obtained through a preset calculation method. It is used to characterize the relative importance of each disaster-affecting factor in disaster assessment for different target areas. It should be noted that when different target areas encounter the same type of disaster, the target weight values ​​corresponding to multiple disaster-affecting factors for different target areas will be different.

[0055] For example, in a flood disaster, the affected area may include multiple target areas, such as area A and area B. Historical disaster data and multiple disaster-influencing factors for areas A and B can be obtained separately. The historical disaster data and multiple disaster-influencing factors for each target area during this flood disaster are then input into multiple pre-trained weight detection models. This yields multiple initial weight values ​​for the total resident population, population density, and flood prevention and mitigation capacity index corresponding to area A, and multiple initial weight values ​​for the total resident population, population density, and flood prevention and mitigation capacity index corresponding to area B. Further, based on a preset calculation method, target weight values ​​for the total resident population, population density, and flood prevention and mitigation capacity index of area A are determined using these initial weight values. Based on a preset calculation method, the target weight values ​​for the total resident population, population density, and flood prevention and mitigation capacity index of region B are determined using multiple initial weight values ​​for the total resident population, population density, and flood prevention and mitigation capacity index. This allows for more accurate weight values ​​tailored to the specific circumstances of each target region, thereby improving the labeling accuracy of disaster-stricken areas.

[0056] S130. Obtain the regional identification map and disaster data of the target area, divide the regional identification map into multiple sub-regions, obtain the disaster influencing factor data corresponding to the disaster influencing factors of each sub-region, and mark the regional identification map with disaster data based on the disaster data of the target area, the multiple disaster influencing factor data and their corresponding target weight values.

[0057] The regional identification map can be a graphic or image used to represent the geospatial information of the target area. Sub-regions can be multiple smaller, relatively independent geographical units into which the regional identification map is divided. Sub-regions can be multiple areas obtained by rasterizing the regional identification map, or they can be areas divided based on factors such as topography, disaster impact range, etc. This embodiment of the invention does not specify the method of sub-region division; those skilled in the art can divide the regional identification map into multiple sub-regions according to annotation requirements. By dividing into sub-regions, the disaster situation in different parts of the target area can be analyzed in more detail, providing a basis for formulating targeted disaster relief and rescue strategies, thereby improving disaster relief efficiency.

[0058] Among them, the disaster data of the target area can be individual disaster element values ​​related to the disaster category and disaster situation of the target area, such as the disaster-affected population, the affected area of ​​crops, the area of ​​crops with no harvest, the number of collapsed houses, or direct economic losses in the target area during floods or other disasters.

[0059] The disaster impact factor data can be the disaster impact factor values ​​corresponding to the disaster impact factors in the sub-region. This data is used to characterize the numerical values ​​of the disaster impact factors in a single natural disaster within the sub-region. The disaster impact factor data can be generated based on monitoring information or obtained through statistical analysis. This embodiment of the invention does not specifically limit the method of obtaining the data corresponding to the disaster impact factors; those skilled in the art can obtain it in different ways according to their needs.

[0060] Specifically, the process involves acquiring a regional identification map and disaster data corresponding to the target area. The regional identification map is then divided into multiple sub-regions. Disaster influencing factor data corresponding to the disaster influencing factors in each sub-region is obtained. Based on the target area disaster data, the multiple disaster influencing factor data, and their corresponding target weight values, the regional identification map is labeled with disaster information. This can be achieved by first acquiring the regional identification map and target area disaster data corresponding to the target area (i.e., the disaster-stricken area requiring disaster labeling), and then dividing the regional identification map into multiple corresponding sub-regions. Further, disaster influencing factor data corresponding to the disaster influencing factors in each sub-region is obtained, i.e., the specific numerical values ​​of the disaster influencing factors for each sub-region. Then, based on the target area disaster data, the multiple disaster influencing factor data, and their corresponding target weight values, the regional identification map is labeled with disaster information to visually display the disaster situation and severity in different sub-regions within the target area. This allows for a more accurate determination of the disaster's impact range and the degree of disaster in each sub-region, providing a data foundation for disaster relief and rescue strategies in the affected area and improving disaster relief efficiency.

[0061] This invention, through obtaining historical disaster data of a target area, inputs this historical disaster data and multiple disaster-related influencing factors into multiple pre-trained weight detection models trained based on machine learning models. Each weight detection model outputs an initial weight value corresponding to each disaster-related influencing factor. For each disaster-related influencing factor, the initial weight values ​​output by the multiple weight detection models are processed into target weight values ​​according to a preset calculation method of averaging or weighted summation. This allows for more accurate determination of the weight value corresponding to each disaster-related influencing factor included in each type of disaster. Furthermore, the invention acquires a regional identification map and disaster data for the target area, divides the regional identification map into multiple sub-regions, and obtains disaster-related influencing factor data for each sub-region. Based on the disaster data of the target area, the multiple disaster-related influencing factor data, and their corresponding target weight values, the regional identification map is labeled with disaster information, improving the efficiency and accuracy of disaster assessment in affected areas.

[0062] Example 2

[0063] Figure 2 This is a flowchart of another disaster labeling method for disaster-stricken areas provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further refines the method of labeling the regional identification map based on disaster data of the target area, multiple disaster-influencing factor data, and their corresponding target weight values. Specifically, it involves determining the target disaster element value for each sub-region based on the disaster data of the target area, multiple disaster-influencing factor data, and their corresponding target weight values; determining the regional labeling information corresponding to each sub-region based on the target disaster element values ​​of multiple sub-regions; and labeling the sub-regions in the regional identification map based on the regional labeling information. For example... Figure 2 As shown, the method in this embodiment may include:

[0064] S210. Obtain historical disaster data for the target area, input the historical disaster data and multiple disaster influencing factors into multiple pre-trained weight detection models, and obtain the initial weight value corresponding to each disaster influencing factor output by each weight detection model.

[0065] S220. For each disaster-affecting factor, the initial weight values ​​output by multiple weight detection models corresponding to the disaster-affecting factor are processed into target weight values ​​corresponding to the disaster-affecting factor according to the preset calculation method; wherein, the preset calculation method includes averaging calculation or weighted summation calculation.

[0066] S230. Obtain the area identification map and disaster data of the target area, divide the area identification map into multiple sub-areas, obtain the disaster influencing factor data corresponding to the disaster influencing factors of each sub-area, and determine the target disaster element value of each sub-area based on the disaster data of the target area, the multiple disaster influencing factor data and their corresponding target weight values.

[0067] Among them, the target disaster element value can be determined based on the regional disaster data corresponding to each sub-region in the target region, multiple disaster influencing factors and their corresponding target weight values, and is used to characterize the severity or impact of the disaster in a single sub-region in the target region.

[0068] Optionally, the target disaster element value for each sub-region is determined based on the disaster data of the target area, the data of multiple disaster influencing factors, and their corresponding target weight values. This includes: for a single sub-region, acquiring the disaster influencing factor data corresponding to the disaster influencing factors of the sub-region, and normalizing the disaster influencing factor data to obtain the target disaster data corresponding to the disaster influencing factor data; and determining the target disaster element value for each sub-region based on the disaster data of the target area, the target disaster data corresponding to the disaster influencing factor data of each sub-region, and the target weight data.

[0069] The target disaster data can be obtained by normalizing the data of multiple disaster influencing factors corresponding to a sub-region through a pre-built normalization algorithm, resulting in disaster data corresponding to each disaster influencing factor.

[0070] Optionally, the target disaster element value for each sub-region can be determined using the following formula: target area disaster data, target disaster data corresponding to the disaster influencing factors data for each sub-region, and target weight data:

[0071]

[0072] Among them, L i L represents the target disaster element value for the i-th sub-region within the target region. S For disaster data in the target area, W k Let value be the target weight value of the k-th disaster impact factor in the target area. ik Let m be the target disaster data for the k-th disaster influencing factor in the i-th sub-region, m be the total number of sub-regions included in the target region, and n be the total number of disaster influencing factors.

[0073] S240. Determine the regional labeling information for each sub-region based on the target disaster element values ​​of multiple sub-regions, and label the sub-regions in the regional identification map based on the regional labeling information.

[0074] The regional labeling information can be determined based on the target disaster element values ​​of each sub-region, and can distinguish different degrees of disaster severity corresponding to the target disaster element values ​​of each sub-region. The regional labeling information can be color information or numerical information, etc. This embodiment of the invention does not specifically limit the specific representation of the regional labeling information; those skilled in the art can set it according to their needs. For example, the regional labeling information corresponding to each sub-region can be determined based on a pre-constructed labeling information mapping table and the target disaster element values ​​corresponding to each sub-region; alternatively, after determining the target disaster element values ​​corresponding to all sub-regions in the target region, the regional labeling information corresponding to each sub-region can be determined based on the sorting result of the target disaster element values ​​of multiple sub-regions. This embodiment of the invention does not specifically limit the method of determining the regional labeling information; those skilled in the art can choose according to their needs.

[0075] Optionally, based on the target disaster element values ​​of multiple sub-regions, determine the area labeling information corresponding to each sub-region, and label the sub-regions in the area identification map according to the area labeling information, including: determining the target labeling color corresponding to each sub-region based on the target disaster element values ​​of multiple sub-regions, and labeling the sub-regions in the area identification map according to the target labeling color.

[0076] The target label color can be determined based on the target disaster element values ​​for each sub-region, and is used to visually distinguish the severity of disasters in different sub-regions on the regional identification map. Target label colors can characterize the disaster situation in sub-regions, improving the efficiency and accuracy of disaster assessment. Furthermore, it allows disaster relief personnel to quickly understand the extent of damage in each region, thereby enabling the development of more precise disaster relief and assistance strategies.

[0077] Specifically, this can be achieved by determining the corresponding regional labeling information for each sub-region based on the target disaster element values ​​of multiple sub-regions, and then labeling the sub-regions in the regional identification map based on the regional labeling information, resulting in a labeled regional identification map. Determining the regional labeling information for each sub-region based on the target disaster element values ​​of multiple sub-regions within a target area, and accurately labeling multiple sub-regions in the regional identification map using this information, allows disaster relief personnel to more intuitively observe the disaster situation in the target area, thereby improving the accuracy and efficiency of disaster assessment and enhancing the efficiency of disaster relief decision-making.

[0078] This invention, through obtaining historical disaster data of a target area, inputs this historical disaster data and multiple disaster-related influencing factors into multiple pre-trained weight detection models trained based on machine learning models. Each weight detection model outputs an initial weight value corresponding to each disaster-related influencing factor. For each disaster-related influencing factor, the initial weight values ​​output by the multiple weight detection models are processed into target weight values ​​according to a preset calculation method of averaging or weighted summation. This allows for more accurate determination of the weight value corresponding to each disaster-related influencing factor included in each type of disaster. Furthermore, the invention acquires a regional identification map and disaster data for the target area, divides the regional identification map into multiple sub-regions, and obtains disaster-related influencing factor data for each sub-region. Based on the disaster data of the target area, the multiple disaster-related influencing factor data, and their corresponding target weight values, the regional identification map is labeled with disaster information, improving the efficiency and accuracy of disaster assessment in affected areas.

[0079] Example 3

[0080] Figure 3 This is a structural schematic diagram of a disaster situation marking device for a disaster-stricken area provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the device includes: an initial weight value determination module 310, a target weight value determination module 320, and a disaster labeling module 330. The initial weight value determination module 310 is used to acquire historical disaster data of the target area, input the historical disaster data and multiple disaster influencing factors into multiple pre-trained weight detection models, and obtain the initial weight value corresponding to each disaster influencing factor output by each weight detection model; wherein, the disaster influencing factors are associated with the disaster type; the weight detection models are trained based on machine learning models; the target weight value determination module 320 is used to process the initial weight values ​​corresponding to the disaster influencing factors output by multiple weight detection models into target weight values ​​corresponding to the disaster influencing factors according to a preset calculation method for each disaster influencing factor; wherein, the preset calculation method includes averaging or weighted summation; the disaster labeling module 330 is used to acquire the regional identification map and disaster data of the target area, divide the regional identification map into multiple sub-areas, acquire the disaster influencing factor data corresponding to the disaster influencing factors of each sub-area, and label the regional identification map with disaster data according to the disaster data of the target area, the multiple disaster influencing factor data and their corresponding target weight values.

[0081] The disaster types include at least one of the following: floods, typhoons, low-temperature freezing disasters, snow and ice disasters, and droughts. The disaster impact factors corresponding to floods include at least one of the following during the initial period of the flood disaster: average rainfall, maximum single-day rainfall, cumulative rainfall, flooded area, maximum flood depth, total flood duration, river network density, distance from the regional center to the river channel, topographic index, topographic slope, soil type, vegetation index, total resident population, population density, cultivated land area, number of houses, house structure, GDP, per capita GDP, and flood prevention and mitigation capacity index. The disaster impact factors corresponding to typhoons include at least one of the following during the initial period of the typhoon disaster: average rainfall, maximum single-day rainfall, cumulative rainfall, flooded area, maximum flood depth, total flood duration, maximum wind speed, average wind speed, river network density, distance from the regional center to the river channel, topographic index, topographic slope, soil type, vegetation index, total resident population, population density, cultivated land area, number of houses, house structure, GDP, per capita GDP, and flood prevention and mitigation capacity index. The factors affecting the disaster situation corresponding to low-temperature freezing disasters include at least one of the following: average daily rainfall, duration of precipitation, average daily temperature, duration of freezing, total resident population, road length, cultivated land area, total length of power lines, GDP, GDP per capita, and the low-temperature freezing disaster prevention and mitigation capacity index. The factors affecting the disaster situation corresponding to snow and ice disasters include at least one of the following: cumulative snowfall, snow depth, duration of snow cover, total resident population, cultivated land area, number of livestock farmers, number of livestock, GDP, GDP per capita, and the snow and ice disaster prevention and mitigation capacity index. The factors affecting the disaster situation corresponding to drought disasters include at least one of the following: meteorological drought comprehensive monitoring index, percentage of rainfall anomaly, percentage of hydrological runoff anomaly, total resident population, number of agricultural population, cultivated land area, area of ​​grain crops, number of livestock, GDP, GDP per capita, and the drought disaster prevention and mitigation capacity index.

[0082] Furthermore, the disaster labeling module 330 includes a disaster element value determination unit 331 and a disaster labeling unit 332. The disaster element value determination unit 331 is used to determine the target disaster element value of each sub-region based on the disaster data of the target area, the data of multiple disaster influencing factors, and their corresponding target weight values; the disaster labeling unit 332 is used to determine the area labeling information corresponding to each sub-region based on the target disaster element values ​​of the multiple sub-regions, and to label the sub-regions in the area identification map based on the area labeling information.

[0083] Furthermore, the disaster labeling device for the affected area also includes a weight detection model, which is used to acquire sample disaster data, multiple sample disaster influencing factor data, and weight labeling information corresponding to each sample disaster influencing factor data. A sample set is constructed based on the sample disaster data, multiple sample disaster influencing factor data, and the weight labeling information corresponding to each sample disaster influencing factor data. The sample set is then input into multiple pre-built machine learning models to train each machine learning model. When the machine learning model meets the preset termination conditions, the machine learning model is determined as the weight detection model.

[0084] Furthermore, the disaster element value determination unit 331 is specifically used to acquire disaster influencing factor data corresponding to the disaster influencing factors corresponding to the sub-region for a single sub-region, and to normalize the disaster influencing factor data to obtain target disaster data corresponding to the disaster influencing factor data; and to determine the target disaster element value of each sub-region based on the target region disaster data, the target disaster data corresponding to the disaster influencing factor data of each sub-region, and the target weight data.

[0085] Furthermore, the disaster element value determination unit 331 is also specifically used to determine the target disaster element value of each sub-region using the target area disaster data, the target disaster data corresponding to the disaster influencing factor data of each sub-region, and the target weight data as described in the following formula:

[0086]

[0087] Among them, L i L represents the target disaster element value for the i-th sub-region within the target region. S For disaster data in the target area, W k Let value be the target weight value of the k-th disaster impact factor in the target area. ik Let m be the target disaster data for the k-th disaster impact factor in the i-th sub-region, m be the total number of sub-regions included in the target region, and n be the total number of disaster impact factors.

[0088] The area labeling information includes color information; furthermore, the disaster labeling unit 332 is specifically used to determine the target labeling color corresponding to each sub-region based on the target disaster element values ​​of multiple sub-regions, and to label the sub-regions in the area identification map according to the target labeling color.

[0089] The disaster labeling device provided in the embodiments of the present invention can execute the disaster labeling device method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0090] Example 4

[0091] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0092] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0094] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as disaster labeling methods for disaster-stricken areas.

[0095] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0096] In some embodiments, the disaster labeling method for disaster-stricken areas may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the disaster labeling method for disaster-stricken areas described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the disaster labeling method for disaster-stricken areas by any other suitable means (e.g., by means of firmware).

[0097] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0099] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0100] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0101] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0102] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0103] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0104] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for marking disaster conditions in a disaster-stricken area, characterized in that, include: Historical disaster data for the target area is acquired, and the historical disaster data and multiple disaster influencing factors are input into multiple pre-trained weight detection models to obtain the initial weight value output by each weight detection model corresponding to each disaster influencing factor; wherein, the disaster influencing factors are associated with the disaster type; the weight detection models are trained based on machine learning models; For each of the disaster-affecting factors, the initial weight values ​​corresponding to the disaster-affecting factors output by multiple weight detection models are processed into target weight values ​​corresponding to the disaster-affecting factors according to a preset calculation method; wherein, the preset calculation method includes averaging or weighted summation. Obtain the regional identification map and disaster data of the target area, divide the regional identification map into multiple sub-regions, obtain the disaster influencing factor data corresponding to the disaster influencing factors of each sub-region, and annotate the regional identification map with disaster data based on the disaster data of the target area, the multiple disaster influencing factor data and their corresponding target weight values.

2. The method according to claim 1, characterized in that, The step of labeling the area identification map with disaster data based on the target area disaster data, multiple disaster influencing factor data, and their corresponding target weight values ​​includes: The target disaster element value for each sub-region is determined based on the disaster data of the target area, the data of multiple disaster influencing factors and their corresponding target weight values; Based on the target disaster element values ​​of the multiple sub-regions, the corresponding area labeling information is determined for each sub-region, and the sub-regions in the area identification map are labeled according to the area labeling information.

3. The method according to claim 1, characterized in that, The weighted detection model is trained in the following manner: Obtain sample disaster data, multiple sample disaster influencing factor data, and weight labeling information corresponding to each sample disaster influencing factor data in the sample area; construct a sample set based on the sample disaster data, multiple sample disaster influencing factor data, and weight labeling information corresponding to each sample disaster influencing factor data. The sample set is input into multiple pre-built machine learning models to train each machine learning model. If a machine learning model meets a preset end-of-training condition, the machine learning model is determined as the weight detection model.

4. The method according to claim 2, characterized in that, The step of determining the target disaster element value for each sub-region based on the disaster data of the target region, multiple disaster influencing factor data, and their corresponding target weight values ​​includes: For each of the sub-regions, disaster impact factor data corresponding to the disaster impact factors of the sub-regions are obtained, and the disaster impact factor data is normalized to obtain target disaster data corresponding to the disaster impact factor data; The target disaster element value for each sub-region is determined based on the disaster data of the target region, the target disaster data corresponding to the disaster influencing factor data of each sub-region, and the target weight data.

5. The method according to claim 4, characterized in that, The target disaster element value for each sub-region is determined using the target area disaster data, the target disaster data corresponding to the disaster influencing factor data for each sub-region, and the target weight data, as described in the following formula: Among them, L i L represents the target disaster element value for the i-th sub-region within the target region. S For disaster data in the target area, W k Let value be the target weight value of the k-th disaster impact factor in the target area. ik Let m be the target disaster data for the k-th disaster impact factor in the i-th sub-region, m be the total number of sub-regions included in the target region, and n be the total number of disaster impact factors.

6. The method according to claim 2, characterized in that, The area labeling information includes color information; the step of determining area labeling information corresponding to each of the multiple sub-regions based on the target disaster element values ​​of the sub-regions, and labeling the sub-regions in the area identification map according to the area labeling information, includes: Based on the target disaster element values ​​of the multiple sub-regions, a target label color corresponding to each sub-region is determined, and the sub-regions in the area identification map are labeled according to the target label color.

7. The method according to claim 1, characterized in that, in, The disaster types include at least one of the following: floods, typhoons, low-temperature freezing disasters, snow and ice disasters, and droughts. The disaster-affecting factors corresponding to the aforementioned flood disaster include at least one of the following during the initial period of the flood disaster: average rainfall in the affected area, maximum single-day rainfall, cumulative rainfall, flood inundation area, maximum flood inundation depth, total flood inundation duration, river network density, distance from the regional center to the river channel, topographic index, topographic slope, soil type, vegetation index, total resident population, population density, cultivated land area, number of houses, house structure, gross domestic product, per capita gross domestic product, and flood prevention and mitigation capacity index. The disaster impact factors corresponding to the typhoon disaster include at least one of the following during the initial period of the typhoon disaster: average rainfall, maximum single-day rainfall, cumulative rainfall, flooded area, maximum flood depth, total flood duration, maximum wind speed, average wind speed, river network density, distance from the regional center to the river channel, topographic index, topographic slope, soil type, vegetation index, total resident population, population density, cultivated land area, number of houses, house structure, gross domestic product, per capita gross domestic product, and typhoon disaster prevention and mitigation capacity index. The disaster-affecting factors corresponding to the aforementioned low-temperature freezing disaster include at least one of the following during the initial period of the low-temperature freezing disaster: average daily rainfall, duration of precipitation, average daily temperature, duration of freezing, total resident population, length of highways, area of ​​cultivated land, total length of power lines, gross domestic product, per capita gross domestic product, and low-temperature freezing disaster prevention and mitigation capacity index. The disaster-related factors corresponding to the aforementioned snow and ice disasters include at least one of the following in the affected area during the initial period of the snow and ice disaster: cumulative snowfall, snow depth, snow duration, total resident population, cultivated land area, number of livestock workers, number of livestock, gross domestic product, and per capita gross domestic product. The disaster-affecting factors corresponding to the drought disaster include at least one of the following in the disaster-affected area during the initial period of the drought disaster: meteorological drought comprehensive monitoring index, rainfall anomaly percentage, hydrological runoff anomaly percentage, total resident population, agricultural population, cultivated land area, grain crop planting area, livestock number, GDP and per capita GDP.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the disaster labeling method for disaster-stricken areas as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the disaster labeling method for any of claims 1-7.

10. A computer program product comprising a computer program / instructions, wherein, When the computer program / instruction is executed by the processor, it implements the disaster situation labeling method for the disaster-stricken area as described in any one of claims 1-7.

Images